Particle Swarm Optimization trained recurrent neural network for voltage instability prediction

Ibrahim, Amr M.; El-Amary, Noha H.

doi:10.1016/j.jesit.2017.05.001

Cited by 35 publications

(19 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because the simplicity and robust performance, PSO attract researcher and engineer [16]. PSO has been widely applied for solving realworld optimization problems, including feature selection [17], Control System in an Internet of Things (IoT) Environment [18], tracking 3D objects in RGB-D image [19], Path Planning For Mobile Robot [20], Face recognition [21], trained recurrent neural network [22], Network Security [23], Gene selection [24], digital image watermarking [25], design digital A proportional-integral-derivative controller (PID), and in various science and engineering problems [16].…”

Section: Particle Swarm Optimization (Pso)mentioning

confidence: 99%

A particle swarm optimization levy flight algorithm for imputation of missing creatinine dataset

Ismail

Aziz

Ralib

et al. 2021

Int. J. Adv. Intell. Informatics

View full text Add to dashboard Cite

Clinicians could intervene during what may be a crucial stage for preventing permanent kidney injury if patients with incipient Acute Kidney Injury (AKI) and those at high risk of developing AKI could be identified. This paper proposes an improved mechanism to machine learning imputation algorithms by introducing the Particle Swarm Levy Flight algorithm. We improve the algorithms by modifying the Particle Swarm Optimization Algorithm (PSO), by enhancing the algorithm with levy flight (PSOLF). The creatinine dataset that we collected, including AKI diagnosis and staging, mortality at hospital discharge, and renal recovery, are tested and compared with other machine learning algorithms such as Genetic Algorithm and traditional PSO. The proposed algorithms' performances are validated with a statistical significance test. The results show that SVMPSOLF has better performance than the other method. This research could be useful as an important tool of prognostic capabilities for determining which patients are likely to suffer from AKI, potentially allowing clinicians to intervene before kidney damage manifests.

show abstract

Section: Particle Swarm Optimization (Pso)mentioning

confidence: 99%

A particle swarm optimization levy flight algorithm for imputation of missing creatinine dataset

Ismail

Aziz

Ralib

et al. 2021

Int. J. Adv. Intell. Informatics

View full text Add to dashboard Cite

show abstract

“…Several research uses deep learning to assess predictions. Certain researchers apply RNN to predict voltage instability [11], early-stage malware with an accuracy of up to 94% [12], air quality [13], and network traffic prediction [14]. Kaneko and Yada [15] applied deep learning to predict sales from retail stores with an accuracy of up to 86%.…”

Section: Related Workmentioning

confidence: 99%

Predictive Delivery Man Assignment Problem using Deep Learning

Juarsa

Djatna

2021

MST

View full text Add to dashboard Cite

Dispatching is a critical part in current online shopping. It relates to how the delivery man assignment should minimize cost along with the service from a source to an end customer with an appropriate scheduled time. The problem arises as neither enough products to deliver nor delivery men are available for dispatch, resulting in suboptimal service and a waste of money. The study aimed to formulate the cost of restaurant dispatching for inducing a deep learning-based solution with the gated recurrent unit recurrent neural network to receive hourly order data and to engage the result for near feature delivery man schedule with minimum cost. The result showed that cost formulation minimized the number of delivery men times the wage per hour with the constraints of each delivery man carrying a maximum of five orders in one way and 11 work hours/day. The deep learning input model used 1078 historical data which were filtered using the Savitzky-Golay method. The root mean square errors of training and testing were 2.35 and 2.41, respectively. Moreover, the number of delivery men every hour was found in a range from one to four people. Furthermore, the deep learning approach saved costs of up to 43.8%. AbstrakPrediksi Masalah Penugasan Kurir dengan Pembelajaran Mendalam. Pengiriman merupakan salah satu hal yang penting dalam model belanja online. Hal itu berhubungan dengan bagaimana penugasan kurir untuk mengantar pesanan hingga ke konsumen dengan cepat dan biaya yang ditimbulkan sesedikit mungkin. Permasalahan yang terjadi adalah jika ada ketidakseimbangan antara jumlah kurir dan jumlah pesanan yang harus diantarkan sehingga menyebabkan pelayanan tidak optimal dan berakhir pemborosan. Tujuan dari penelitian ini adalah memformulasi model biaya pengiriman yang terdapat di restoran, menyusun solusi deep learning gated recurrent Unit (GRU) recurrent neural network (RNN) untuk mendapatkan data pesanan setiap jam, dan menggunakan hasil yang didapat untuk menyusun jadwal penugasan kurir yang menghasilkan biaya minimum. Hasil yang didapat adalah formulasi dari biaya penugasan adalah meminimumkan jumlah kurir dikali dengan upah tiap jamnya, dengan batasan masing-masing kurir maksimum membawa 5 pesanan dalam sekali jalan dan 11 jam kerja/hari. Input dalam model deep learning adalah 1078 data historis pesanan online yang sudah disaring menggunakan metode Savitzky-Golay. RMSE dari data pelatihan dan data percobaan masing-masing 2.35 dan 2.41. Jumlah kurir yang didapat dari metode ini adalah 1-4 orang dari yang sebelumnya 3-4 orang. Metode ini mampu menghemat biaya hingga 43.8%.

show abstract

“…Numerous studies have been proposed to identify ability of PSO as an effective training algorithm for NN. The studies showed that PSO has a very high capability for training BPNN [27][28][29][30][31][32]. Although some attempts have been made to use other optimization search techniques for training the weights, it has been found that the results obtained by PSO-BPNN provides higher accuracy when compared to other algorithms [33].…”

Section: Particle Swarm Optimization For Training Backpropagation Neumentioning

confidence: 99%

Thailand port throughput prediction via particle swarm optimization based neural network

Kunnapapdeelert¹,

Thepmongkorn²

2020

J Appl Eng Science

View full text Add to dashboard Cite

Shipping volume in Thailand have signifi cantly increased in last four years. It is important to pay attention to the trend of Thailand port throughput and use as the guideline to prepare for the needs of supporting facilities, infrastructures, fi nancial and human resources. An effective forecasting technique called particle swarm based neural network (PSO-NN) is developed to estimate Thailand port throughput in this work. The prediction results from PSONN and classical backpropagation training algorithm, backpropagation neural networks (BPNN) were compared. The results shown that PSONN provides more accurate results than BPNN when apply to predict port throughput of Thailand. The mean squared error obtained from PSONN are about 10 times lower than that of BPNN. This confi rms that neural network based on PSO training algorithm has better performance and better ability to escape local optimum than that of BPNN.

show abstract

Particle Swarm Optimization trained recurrent neural network for voltage instability prediction

Cited by 35 publications

References 11 publications

A particle swarm optimization levy flight algorithm for imputation of missing creatinine dataset

A particle swarm optimization levy flight algorithm for imputation of missing creatinine dataset

Predictive Delivery Man Assignment Problem using Deep Learning

Thailand port throughput prediction via particle swarm optimization based neural network

Contact Info

Product

Resources

About